pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2019 1

verdicts

UNVERDICTED 1

representative citing papers

Investigating Biases in Textual Entailment Datasets

cs.CL · 2019-06-23 · unverdicted · novelty 5.0

Hypothesis-only classification reaches 64% accuracy on SNLI, revealing dataset biases in SNLI and MultiNLI that the authors quantify and propose a simple mitigation for.

citing papers explorer

Showing 1 of 1 citing paper.

  • Investigating Biases in Textual Entailment Datasets cs.CL · 2019-06-23 · unverdicted · none · ref 2

    Hypothesis-only classification reaches 64% accuracy on SNLI, revealing dataset biases in SNLI and MultiNLI that the authors quantify and propose a simple mitigation for.